Sequentially accumulating attention-weighted context from previously linked entities, one pass per document, improves entity-linking accuracy over joint global inference and reduces inference cost from roughly quadratic to linear in the number of mentions.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Dynamic Context Augmentation for Global Entity Linking
Sequentially accumulating attention-weighted context from previously linked entities, one pass per document, improves entity-linking accuracy over joint global inference and reduces inference cost from roughly quadratic to linear in the number of mentions.